检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Xi, Xuanyang Luo, Yongkang Li, Fengfu Wang, Peng Qiao, Hong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China Research Center of Precision Sensing and Control Institute of Automation Chinese Academy of Sciences Beijing100190 China LSEC Institute of Applied Mathematics AMSS Chinese Academy of Sciences Beijing100190 China

Visual saliency detection aims at identifying the most visually distinctive parts in an image, and serves as a pre-processing step for a variety of computer vision and image processing tasks. To this end, the saliency detection procedure must be as fast and compact as possible and optimally processes input images in a real time manner. It is an essential application requirement for the saliency detection task. However, contemporary detection methods often utilize some complicated procedures to pursue feeble improvements on the detection precession, which always take hundreds of milliseconds and make them not easy to be applied practically. In this paper, we tackle this problem by proposing a fast and compact saliency score regression network which employs fully convolutional network, a special deep convolutional neural network, to estimate the saliency of objects in images. It is an extremely simplified end-to-end deep neural network without any pre-processings and post-processings. When given an image, the network can directly predict a dense full-resolution saliency map (image-to-image prediction). It works like a compact pipeline which effectively simplifies the detection procedure. Our method is evaluated on six public datasets, and experimental results show that it can achieve comparable or better precision performance than the state-of-the-art methods while get a significant improvement in detection speed (35 FPS, processing in real time). Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Social role clustering with topic model

Social role clustering with topic model

引用

IEEE International Conference on Intelligence and Security Informatics, ISI

作者： Jie Bai Linjing Li Daniel Zeng Junjie Lin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation China School of Computer and Control Engineering University of Chinese Academy of Sciences China Department of Management of Information Systems The University of Arizona USA

ISBN: (纸本)9781509038664

In this paper, we propose a new role analyzing paradigm for social networks enlightened by topic modeling, which can be adopted as a primitive building block in various security related tasks, such as hidden community finding, important person recognizing and so on. We first present the social network under analyzing as a heterogeneous network constructed by both the users and the subjects discussed among them. We then view this network in a Bag-of-Users schema, which mimics its classical Bag-of-Words counterpart. In this schema, the subjects discussed are treated as “documents” while the users are treated as “words” which construct the “documents”. Based on this novel presentation, we finally apply topic modeling technology to perform the social role clustering. Experiments on a practical security-related social network dataset prove the effectiveness of our approach.

关键词： Social network services Heterogeneous networks Analytical models Computational modeling Finance Security Data models

来源：评论

学校读者我要写书评

暂无评论

A General Adaptive Dynamic Programming Approach with Experience Replay

A General Adaptive Dynamic Programming Approach with Experie...

引用

International Joint Conference on Neural Networks

作者： Bin Wang Dongbin Zhao Jin Cheng Yuan Xu Yueyang Li School of Electrical Engineering University of Jinan The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781509006212

Experience replay is a promising approach to improve the learning efficiency of adaptive dynamic programming. A general model-free adaptive dynamic programming (ADP) approach with the experience replay technology is investigated in this paper to solve the optimal control problems in continuous state and action spaces. Both the critic network and action network are modeled with a feedforward neural network with one hidden layer. During the learning process, a number of recently observed data samples are recorded in a database. When updating the parameters of the neural networks, the data in the sample database are repeatedly used to update the weights of the action network and the critic network. Implementation details of the algorithm are given, and simulation experiments are utilized to verify the learning efficiency of the proposed approach.

关键词： Erbium Dynamic programming Neural networks Databases Optimal control Heuristic algorithms Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel policy iteration based deterministic Q-learning for discrete-time nonlinear systems

引用

Science China(Information Sciences) 2015年第12期58卷 147-161页

作者： WEI QingLai LIU DeRong State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences School of Automation and Electrical Engineering University of Science and Technology Beijing

In this paper, a novel iterative Q-learning algorithm, called "policy iteration based deterministic Qlearning algorithm", is developed to solve the optimal control problems for discrete-time deterministic nonlinear systems. The idea is to use an iterative adaptive dynamic programming(ADP) technique to construct the iterative control law which optimizes the iterative Q function. When the optimal Q function is obtained, the optimal control law can be achieved by directly minimizing the optimal Q function, where the mathematical model of the system is not necessary. Convergence property is analyzed to show that the iterative Q function is monotonically non-increasing and converges to the solution of the optimality equation. It is also proven that any of the iterative control laws is a stable control law. Neural networks are employed to implement the policy iteration based deterministic Q-learning algorithm, by approximating the iterative Q function and the iterative control law, respectively. Finally, two simulation examples are presented to illustrate the performance of the developed algorithm.

关键词： adaptive critic designs adaptive dynamic programming approximate dynamic programming Q learning policy iteration neural networks nonlinear systems optimal control

来源：评论

学校读者我要写书评

暂无评论

An overall solution of Virtual Reality Classroom

An overall solution of Virtual Reality Classroom

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Xisong Dong The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Institute of Smart Education Systems Qingdao Academy of Intelligent Industries

Virtual Reality(VR) is a three-dimensional computergenerated virtual world. It is essential to introduced VR technology to education area to develop new teaching mode to improve the efficiency and quality of teaching and learning. Among them, VR classroom has quickly become most dazzling star with its subversive advantage. This paper proposes an overall integration solution of VR classroom, including its composition, its scene design of various disciplines and its main advantage. Finally, a case study of a geography lesson is provided to show its advantages and strong potentiality.

关键词： Virtual Reality Education virtual classroom

来源：评论

学校读者我要写书评

暂无评论

How to “STEAM” Children at Home? Let Children “STEAM” Themselves

How to “STEAM” Children at Home? Let Children “STEAM” Th...

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Xiaoyan Gong The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Institute of Smart Education Systems Qingdao Academy of Intelligent Industries

In this article, I would like to share my daughter's experience on self-STEAM education. In our daily life, she can always find problems and then dream them with her imagination, finally narrows down her solutions to solve problems in her own way. During these problem-solving processes, I noticed that she went through sciences, technology, engineering, arts and mathematics in a very natural way. So I would like to say, STEAM is the way we learn and grow ever since we were born. But later at school, we are trained in a way that subjects are completely disconnected. It might take time to change this situation at school, but at home, as parents, we need to realize that children can discover new things by themselves even from young ages, and provide rich learning environment for them and let them "STEAM " themselves in their own way.

关键词： STEM STEAM education maker education

来源：评论

学校读者我要写书评

暂无评论

Activating topic models from a cognitive perspective

Activating topic models from a cognitive perspective

引用

IEEE International Conference on Intelligence and Security Informatics, ISI

作者： Jie Bai Linjing Li Daniel Zeng School of Computer and Control Engineering University of Chinese Academy of Sciences China The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences China Department of Management of Information Systems The University of Arizona USA

ISBN: (纸本)9781509038664

Topic modeling is a popular text mining technique for extracting latent semantics from text. It can be widely applied in intelligence analyzing, anti-terrorist, and various other security related tasks. Most existing topic models only focus exclusively on the text literally, and disregard rich contextual, cultural, and language background, hindering the understanding and discovering of the key clues implied in the text. Based on cognitive psychology theories, we justify the classical psychological activation theory named Adaptive control of Thought from the perspective of information theory. Then, we propose a fast and loosely-coupled activation presentation of text for topic models. Our method mimics the aspect of human cognitive procedure when facing the activation of new concepts based on word correlations and word frequencies. Experimental results on multiple tasks show that our activation presentation models can significantly improve the performance of the topic models with linear time consumption.

关键词： Analytical models Semantics Computational modeling Psychology Text mining Information theory Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Improvement of reliable H control for discrete-time fuzzy systems with time-varying delays

Improvement of reliable H control for discrete-time fuzzy sy...

引用

2016 IEEE International Conference on Fuzzy systems, FUZZ-IEEE 2016

作者： Wang, Shenquan Jiang, Yulian Li, Yuanchun Liu, Derong College of Electrical and Electronic Engineering Changchun University of Technology Changchun130012 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China

ISBN: (纸本)9781509006250

This paper is concerned with the reliable H control problem for discrete-time Takagi-Sugeno (T-S) fuzzy systems with time-varying delays and stochastic actuator faults based on a novel summation inequality. A discrete-time homogeneous Markov chain is used to represent the stochastic behavior of actuator faults. By employing a fuzzy basis-dependent Lyapunov functional and the novel summation inequality, an improved sufficient condition is established to ensure that the resultant closedloop system is stochastically stable with an H performance index. Meanwhile, the solvability condition for the reliable H control is also established, by which the reliable H fuzzy controller can be solved from linear matrix inequalities. A numerical example is provided to demonstrate the effectiveness of the present approach. © 2016 IEEE.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

An Answer Recommendation Algorithm for Medical Community Question Answering systems

An Answer Recommendation Algorithm for Medical Community Que...

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Jing Wang Chuntao Man Yifei Zhao Feiyue Wang College of Automation Harbin University of Science & Technology The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

Online medical community question answering(c QA) systems are playing important roles as a supplement of the traditional medical service systems. The answer recommendation service provides guidance to diagnose diseases and brings convenience and valuable reference to users. In this paper, we propose a method to recommend answer for particular questions on medical c QA system. There are three steps for the answer recommendation system, including similar cases retrieval, answers quality estimation and answer recommendation. The proposed algorithm is tested on a dataset collected from online medical community question answering system. The results show a good performance in answer recommendation.

关键词： medical community question answering systems similar cases retrieval answer quality estimation data mining

来源：评论

学校读者我要写书评

暂无评论

Move prediction in Gomoku using deep learning

Move prediction in Gomoku using deep learning

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Kun Shao Dongbin Zhao Zhentao Tang Yuanheng Zhu The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781509044245

The Gomoku board game is a longstanding challenge for artificial intelligence research. With the development of deep learning, move prediction can help to promote the intelligence of board game agents as proven in AlphaGo. Following this idea, we train deep convolutional neural networks by supervised learning to predict the moves made by expert Gomoku players from RenjuNet dataset. We put forward a number of deep neural networks with different architectures and different hyperparameters to solve this problem. With only the board state as the input, the proposed deep convolutional neural networks are able to recognize some special features of Gomoku and select the most likely next move. The final neural network achieves the accuracy of move prediction of about 42% on the RenjuNet dataset, which reaches the level of expert Gomoku players. In addition, it is promising to generate strong Gomoku agents of human-level with the move prediction as a guide.

关键词： Games Machine learning Neural networks Training Supervised learning Network architecture Computers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：